Title: Combination of machine learning methods to solve cold start problem in recommender system

Authors: Nitin Mishra; Vimal Mishra; Saumya Chaturvedi

Addresses: Dr. A.P.J. Abdul Kalam Technical University, Sector 11, Jankipuram Vistar, Lucknow, Uttar Pradesh 226021, India ' IERT Allahabad, 26, Chatham Line, Dharhariya, Prayagraj, Uttar Pradesh 211002, India ' Dr. A.P.J. Abdul Kalam Technical University, Sector 11, Jankipuram Vistar, Lucknow, Uttar Pradesh 226021, India

Abstract: Recommender systems are a special type of intelligent systems which exploits historical of user rating on items to make the recommendation of items for those users. They are used in a wide range of applications like online shopping, e-commerce services social networking applications and many more. In our paper, we are solving a problem known as the cold start problem where the new user has a problem as he has the missing history. We have validated our solution on MovieLens dataset and found it to be solving cold start problem in a magical way. we claim our approach to be a novel approach for solving cold start problem using a combination of several methods some of which belong to collaborative filtering domain and others belong to content-based domain. We have done exhaustive testing to ensure no fault in the proposed method. The results shown by our method are promising.

Keywords: cold start problem; recommender systems; machine learning; classification; clustering; k-modes clustering.

DOI: 10.1504/IJAIP.2024.143817

International Journal of Advanced Intelligence Paradigms, 2024 Vol.29 No.4, pp.332 - 347

Received: 03 Dec 2018
Accepted: 18 Dec 2018
Published online: 08 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article